skill · Global

Speckle-Claude-Skill-Package

25 deterministic Claude AI skills for Speckle Data Platform. Object model, GraphQL API, Python/C# SDKs, connectors (Revit, Rhino, Blender, AutoCAD, Tekla), viewer, Automate

Visit source ↗GitHub repository ↗

Claim this listing

Represent Speckle-Claude-Skill-Package? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Explore paid sponsorship →

What's in it

Data offered docs-verified: Speckle object model (Base objects, hashing, detached properties) · Transport (ServerTransport, SQLiteTransport, MemoryTransport) · GraphQL API queries (streams, commits, branches, objects) · REST API and authentication · Webhooks · Automate functions · SpecklePy (Python) and Speckle.Sdk (C#) SDK patterns · Connector patterns: Revit, Rhino/Grasshopper, Blender, AutoCAD/Civil3D, Tekla, Power BI · Viewer (@speckle/viewer) · Versioning and cross-model federation · Error diagnosis: transport, conversion, auth
Coverage llm-inferred: Global
Formats docs-verified: Markdown (SKILL.md)
Access docs-verified: Free and open source under the MIT licence. Speckle API use requires a personal access token supplied via the SPECKLE_TOKEN environment variable (or the MCP server env block). Targets self-hosted Speckle Server or app.speckle.systems.

Useful for

Use cases llm-inferred: Generating SpecklePy code that wraps model objects in a Base root with detached '@' properties before operations.send, so the viewer renders them correctly · Diagnosing 401/403 or token-expiry failures when a connector or script cannot reach a Speckle stream · Setting up a Speckle Automate check that validates model property completeness before issue review · Coordinating multi-discipline models (e.g. structural and civils streams) through federation for clash-detection setup
Audience llm-inferred: BIM coordinators · Civils and BIM engineers working with Civil3D, Revit, or Tekla · Computational designers using Rhino/Grasshopper or Blender · Developers building AEC data pipelines in Python or C# · Digital delivery and data teams

Limitations

Constraints llm-inferred: Skills are guidance text for Claude, not a data source; they supply no live model or project data · Live API use needs a Speckle account, a personal access token, and a reachable Speckle Server · The bundled MCP server must be built locally with Node before its tools can be used · SDK and connector skills target 'latest' versions, so content can drift from upstream releases (maintenance risk) · Content is generic Speckle; no UK-specific standards, datums or workflows are evident in the docs · Connector skills cover patterns and mappings only; they do not confirm that a given connector version runs in a given environment

Licence: MIT
Authentication: API key via env: SPECKLE_TOKEN (auto-extracted from README)
GitHub stars: 14
Last commit: 08/07/2026
Last successful page check: 14/10/2026
Page health: healthy
Package: Not recorded
Verification: Not independently verified

Auto-extracted, unverified fields: tools, install, auth. Check upstream documentation.

Provenance & evidence

Daily discovery 2026-10-15: GitHub search; verified via GitHub API. Tools/install/auth auto-extracted from README.

Metadata observed 14/10/2026 · daily-2026-10-15 (github-search)